diff options
Diffstat (limited to 'drivers/firmware/efi/cper.c')
| -rw-r--r-- | drivers/firmware/efi/cper.c | 185 |
1 files changed, 154 insertions, 31 deletions
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c index ea7ca74fc173..0232bd040f61 100644 --- a/drivers/firmware/efi/cper.c +++ b/drivers/firmware/efi/cper.c @@ -12,6 +12,7 @@ * Specification version 2.4. */ +#include <linux/bitmap.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/time.h> @@ -24,8 +25,7 @@ #include <linux/bcd.h> #include <acpi/ghes.h> #include <ras/ras_event.h> - -static char rcd_decode_str[CPER_REC_LEN]; +#include <cxl/event.h> /* * CPER record ID need to be unique even after reboot, because record @@ -70,7 +70,7 @@ const char *cper_severity_str(unsigned int severity) } EXPORT_SYMBOL_GPL(cper_severity_str); -/* +/** * cper_print_bits - print strings for set bits * @pfx: prefix for each line, including log level and prefix string * @bits: bit mask @@ -107,6 +107,65 @@ void cper_print_bits(const char *pfx, unsigned int bits, printk("%s\n", buf); } +/** + * cper_bits_to_str - return a string for set bits + * @buf: buffer to store the output string + * @buf_size: size of the output string buffer + * @bits: bit mask + * @strs: string array, indexed by bit position + * @strs_size: size of the string array: @strs + * + * Add to @buf the bitmask in hexadecimal. Then, for each set bit in @bits, + * add the corresponding string describing the bit in @strs to @buf. + * + * A typical example is:: + * + * const char * const bits[] = { + * "bit 3 name", + * "bit 4 name", + * "bit 5 name", + * }; + * char str[120]; + * unsigned int bitmask = BIT(3) | BIT(5); + * #define MASK GENMASK(5,3) + * + * cper_bits_to_str(str, sizeof(str), FIELD_GET(MASK, bitmask), + * bits, ARRAY_SIZE(bits)); + * + * The above code fills the string ``str`` with ``bit 3 name|bit 5 name``. + * + * Return: number of bytes stored or an error code if lower than zero. + */ +int cper_bits_to_str(char *buf, int buf_size, unsigned long bits, + const char * const strs[], unsigned int strs_size) +{ + int len = buf_size; + char *str = buf; + int i, size; + + *buf = '\0'; + + for_each_set_bit(i, &bits, strs_size) { + if (!(bits & BIT_ULL(i))) + continue; + + if (*buf && len > 0) { + *str = '|'; + len--; + str++; + } + + size = strscpy(str, strs[i], len); + if (size < 0) + return size; + + len -= size; + str += size; + } + return len - buf_size; +} +EXPORT_SYMBOL_GPL(cper_bits_to_str); + static const char * const proc_type_strs[] = { "IA32/X64", "IA64", @@ -213,7 +272,33 @@ const char *cper_mem_err_type_str(unsigned int etype) } EXPORT_SYMBOL_GPL(cper_mem_err_type_str); -static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) +const char *cper_mem_err_status_str(u64 status) +{ + switch ((status >> 8) & 0xff) { + case 1: return "Error detected internal to the component"; + case 4: return "Storage error in DRAM memory"; + case 5: return "Storage error in TLB"; + case 6: return "Storage error in cache"; + case 7: return "Error in one or more functional units"; + case 8: return "Component failed self test"; + case 9: return "Overflow or undervalue of internal queue"; + case 16: return "Error detected in the bus"; + case 17: return "Virtual address not found on IO-TLB or IO-PDIR"; + case 18: return "Improper access error"; + case 19: return "Access to a memory address which is not mapped to any component"; + case 20: return "Loss of Lockstep"; + case 21: return "Response not associated with a request"; + case 22: return "Bus parity error - must also set the A, C, or D Bits"; + case 23: return "Detection of a protocol error"; + case 24: return "Detection of a PATH_ERROR"; + case 25: return "Bus operation timeout"; + case 26: return "A read was issued to data that has been poisoned"; + default: return "Reserved"; + } +} +EXPORT_SYMBOL_GPL(cper_mem_err_status_str); + +int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) { u32 len, n; @@ -221,54 +306,54 @@ static int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg) return 0; n = 0; - len = CPER_REC_LEN - 1; + len = CPER_REC_LEN; if (mem->validation_bits & CPER_MEM_VALID_NODE) - n += scnprintf(msg + n, len - n, "node: %d ", mem->node); + n += scnprintf(msg + n, len - n, "node:%d ", mem->node); if (mem->validation_bits & CPER_MEM_VALID_CARD) - n += scnprintf(msg + n, len - n, "card: %d ", mem->card); + n += scnprintf(msg + n, len - n, "card:%d ", mem->card); if (mem->validation_bits & CPER_MEM_VALID_MODULE) - n += scnprintf(msg + n, len - n, "module: %d ", mem->module); + n += scnprintf(msg + n, len - n, "module:%d ", mem->module); if (mem->validation_bits & CPER_MEM_VALID_RANK_NUMBER) - n += scnprintf(msg + n, len - n, "rank: %d ", mem->rank); + n += scnprintf(msg + n, len - n, "rank:%d ", mem->rank); if (mem->validation_bits & CPER_MEM_VALID_BANK) - n += scnprintf(msg + n, len - n, "bank: %d ", mem->bank); + n += scnprintf(msg + n, len - n, "bank:%d ", mem->bank); if (mem->validation_bits & CPER_MEM_VALID_BANK_GROUP) - n += scnprintf(msg + n, len - n, "bank_group: %d ", + n += scnprintf(msg + n, len - n, "bank_group:%d ", mem->bank >> CPER_MEM_BANK_GROUP_SHIFT); if (mem->validation_bits & CPER_MEM_VALID_BANK_ADDRESS) - n += scnprintf(msg + n, len - n, "bank_address: %d ", + n += scnprintf(msg + n, len - n, "bank_address:%d ", mem->bank & CPER_MEM_BANK_ADDRESS_MASK); if (mem->validation_bits & CPER_MEM_VALID_DEVICE) - n += scnprintf(msg + n, len - n, "device: %d ", mem->device); + n += scnprintf(msg + n, len - n, "device:%d ", mem->device); if (mem->validation_bits & (CPER_MEM_VALID_ROW | CPER_MEM_VALID_ROW_EXT)) { u32 row = mem->row; row |= cper_get_mem_extension(mem->validation_bits, mem->extended); - n += scnprintf(msg + n, len - n, "row: %d ", row); + n += scnprintf(msg + n, len - n, "row:%d ", row); } if (mem->validation_bits & CPER_MEM_VALID_COLUMN) - n += scnprintf(msg + n, len - n, "column: %d ", mem->column); + n += scnprintf(msg + n, len - n, "column:%d ", mem->column); if (mem->validation_bits & CPER_MEM_VALID_BIT_POSITION) - n += scnprintf(msg + n, len - n, "bit_position: %d ", + n += scnprintf(msg + n, len - n, "bit_position:%d ", mem->bit_pos); if (mem->validation_bits & CPER_MEM_VALID_REQUESTOR_ID) - n += scnprintf(msg + n, len - n, "requestor_id: 0x%016llx ", + n += scnprintf(msg + n, len - n, "requestor_id:0x%016llx ", mem->requestor_id); if (mem->validation_bits & CPER_MEM_VALID_RESPONDER_ID) - n += scnprintf(msg + n, len - n, "responder_id: 0x%016llx ", + n += scnprintf(msg + n, len - n, "responder_id:0x%016llx ", mem->responder_id); if (mem->validation_bits & CPER_MEM_VALID_TARGET_ID) - scnprintf(msg + n, len - n, "target_id: 0x%016llx ", - mem->target_id); + n += scnprintf(msg + n, len - n, "target_id:0x%016llx ", + mem->target_id); if (mem->validation_bits & CPER_MEM_VALID_CHIP_ID) - scnprintf(msg + n, len - n, "chip_id: %d ", - mem->extended >> CPER_MEM_CHIP_ID_SHIFT); + n += scnprintf(msg + n, len - n, "chip_id:%d ", + mem->extended >> CPER_MEM_CHIP_ID_SHIFT); - msg[n] = '\0'; return n; } +EXPORT_SYMBOL_GPL(cper_mem_err_location); -static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) +int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) { u32 len, n; const char *bank = NULL, *device = NULL; @@ -287,6 +372,7 @@ static int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg) return n; } +EXPORT_SYMBOL_GPL(cper_dimm_err_location); void cper_mem_err_pack(const struct cper_sec_mem_err *mem, struct cper_mem_err_compact *cmem) @@ -308,11 +394,13 @@ void cper_mem_err_pack(const struct cper_sec_mem_err *mem, cmem->mem_array_handle = mem->mem_array_handle; cmem->mem_dev_handle = mem->mem_dev_handle; } +EXPORT_SYMBOL_GPL(cper_mem_err_pack); const char *cper_mem_err_unpack(struct trace_seq *p, struct cper_mem_err_compact *cmem) { const char *ret = trace_seq_buffer_ptr(p); + char rcd_decode_str[CPER_REC_LEN]; if (cper_mem_err_location(cmem, rcd_decode_str)) trace_seq_printf(p, "%s", rcd_decode_str); @@ -327,6 +415,7 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem, int len) { struct cper_mem_err_compact cmem; + char rcd_decode_str[CPER_REC_LEN]; /* Don't trust UEFI 2.1/2.2 structure with bad validation bits */ if (len == sizeof(struct cper_sec_mem_err_old) && @@ -335,7 +424,9 @@ static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem, return; } if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS) - printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status); + printk("%s error_status: %s (0x%016llx)\n", + pfx, cper_mem_err_status_str(mem->error_status), + mem->error_status); if (mem->validation_bits & CPER_MEM_VALID_PA) printk("%s""physical_address: 0x%016llx\n", pfx, mem->physical_addr); @@ -403,19 +494,24 @@ static void cper_print_pcie(const char *pfx, const struct cper_sec_pcie *pcie, "%s""bridge: secondary_status: 0x%04x, control: 0x%04x\n", pfx, pcie->bridge.secondary_status, pcie->bridge.control); - /* Fatal errors call __ghes_panic() before AER handler prints this */ - if ((pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) && - (gdata->error_severity & CPER_SEV_FATAL)) { + /* + * Print all valid AER info. Record may be from BERT (boot-time) or GHES (run-time). + * + * Fatal errors call __ghes_panic() before AER handler prints this. + */ + if (pcie->validation_bits & CPER_PCIE_VALID_AER_INFO) { struct aer_capability_regs *aer; aer = (struct aer_capability_regs *)pcie->aer_info; + printk("%saer_cor_status: 0x%08x, aer_cor_mask: 0x%08x\n", + pfx, aer->cor_status, aer->cor_mask); printk("%saer_uncor_status: 0x%08x, aer_uncor_mask: 0x%08x\n", pfx, aer->uncor_status, aer->uncor_mask); printk("%saer_uncor_severity: 0x%08x\n", pfx, aer->uncor_severity); printk("%sTLP Header: %08x %08x %08x %08x\n", pfx, - aer->header_log.dw0, aer->header_log.dw1, - aer->header_log.dw2, aer->header_log.dw3); + aer->header_log.dw[0], aer->header_log.dw[1], + aer->header_log.dw[2], aer->header_log.dw[3]); } } @@ -492,6 +588,17 @@ static void cper_print_tstamp(const char *pfx, } } +struct ignore_section { + guid_t guid; + const char *name; +}; + +static const struct ignore_section ignore_sections[] = { + { .guid = CPER_SEC_CXL_GEN_MEDIA_GUID, .name = "CXL General Media Event" }, + { .guid = CPER_SEC_CXL_DRAM_GUID, .name = "CXL DRAM Event" }, + { .guid = CPER_SEC_CXL_MEM_MODULE_GUID, .name = "CXL Memory Module Event" }, +}; + static void cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata, int sec_no) @@ -512,6 +619,14 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata printk("%s""fru_text: %.20s\n", pfx, gdata->fru_text); snprintf(newpfx, sizeof(newpfx), "%s ", pfx); + + for (int i = 0; i < ARRAY_SIZE(ignore_sections); i++) { + if (guid_equal(sec_type, &ignore_sections[i].guid)) { + printk("%ssection_type: %s\n", newpfx, ignore_sections[i].name); + return; + } + } + if (guid_equal(sec_type, &CPER_SEC_PROC_GENERIC)) { struct cper_sec_proc_generic *proc_err = acpi_hest_get_payload(gdata); @@ -568,6 +683,14 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata cper_print_fw_err(newpfx, gdata, fw_err); else goto err_section_too_small; + } else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) { + struct cxl_cper_sec_prot_err *prot_err = acpi_hest_get_payload(gdata); + + printk("%ssection_type: CXL Protocol Error\n", newpfx); + if (gdata->error_data_length >= sizeof(*prot_err)) + cxl_cper_print_prot_err(newpfx, prot_err); + else + goto err_section_too_small; } else { const void *err = acpi_hest_get_payload(gdata); @@ -633,7 +756,7 @@ int cper_estatus_check(const struct acpi_hest_generic_status *estatus) data_len = estatus->data_length; apei_estatus_for_each_section(estatus, gdata) { - if (sizeof(struct acpi_hest_generic_data) > data_len) + if (acpi_hest_get_size(gdata) > data_len) return -EINVAL; record_size = acpi_hest_get_record_size(gdata); |
